Related Experiment Video
Updated: Oct 10, 2025
Murine Fetal Echocardiography
Published on: February 15, 2013
Deep Learning-Based Computer-Aided Fetal Echocardiography: Application to Heart Standard View Segmentation for
Siti Nurmaini1, Muhammad Naufal Rachmatullah1, Ade Iriani Sapitri1
1Intelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang 30139, Indonesia.
Insights
This study introduces a deep learning model for automatic fetal heart segmentation and congenital heart defect (CHD) detection in echocardiography. The AI model accurately identifies standard heart views and detects CHDs, improving diagnostic rates.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Healthcare
- Cardiology
Background:
- Accurate fetal heart segmentation in echocardiography is crucial for diagnosing congenital heart defects (CHDs).
- Current manual segmentation and detection methods are challenging due to anatomical variations and rely heavily on human expertise, leading to variable accuracy.
- The need for automated, reliable tools to improve the accuracy and consistency of CHD diagnosis is significant.
Purpose of the Study:
- To develop and evaluate a deep learning-based computer-aided system for automated fetal heart echocardiography examinations.
- To simultaneously segment standard fetal heart views and detect congenital heart defects (CHDs) using an instance segmentation approach.
- To enhance the accuracy and efficiency of CHD diagnosis through automated image analysis.
Main Methods:
- Proposed a deep learning model employing an instance segmentation approach for fetal heart image analysis.
- Trained and tested the model on 1149 fetal heart images, predicting 24 object types including standard views, heart chambers, and CHD cases.
- Evaluated segmentation performance using Intersection over Union (IoU) and Dice coefficient, and detection performance using mean Average Precision (mAP).
Main Results:
- Achieved satisfactory performance in standard fetal heart view segmentation with 79.97% IoU and 89.70% Dice coefficient.
- Demonstrated strong performance in CHD detection, with mAP of 98.30% for intra-patient variation and 82.42% for inter-patient variation.
- The model successfully segmented four standard views, 17 heart chambers, and detected three types of CHDs.
Conclusions:
- The proposed deep learning model shows significant potential for automating fetal heart segmentation and CHD detection in echocardiography.
- Automated techniques can contribute to improving the accuracy and accessibility of congenital heart disease diagnosis.
- Further development of such AI tools could aid clinicians in early and precise detection of fetal cardiac abnormalities.
Abstract:
Accurate segmentation of fetal heart in echocardiography images is essential for detecting the structural abnormalities such as congenital heart defects (CHDs). Due to the wide variations attributed to different factors, such as maternal obesity, abdominal scars, amniotic fluid volume, and great vessel connections, this process is still a challenging problem. CHDs detection with expertise in general are substandard; the accuracy of measurements remains highly dependent on humans' training, skills, and experience. To make such a process automatic, this study proposes deep learning-based computer-aided fetal heart echocardiography examinations with an instance segmentation approach, which inherently segments the four standard heart views and detects the defect simultaneously. We conducted several experiments with 1149 fetal heart images for predicting 24 objects, including four shapes of fetal heart standard views, 17 objects of heart-chambers in each view, and three cases of congenital heart defect. The result showed that the proposed model performed satisfactory performance for standard views segmentation, with a 79.97% intersection over union and 89.70% Dice coefficient similarity. It also performed well in the CHDs detection, with mean average precision around 98.30% for intra-patient variation and 82.42% for inter-patient variation. We believe that automatic segmentation and detection techniques could make an important contribution toward improving congenital heart disease diagnosis rates.
Related Concept Videos
01:20Imaging Studies for Cardiovascular System II:Types of Echocardiography
Types of Echocardiography
Transthoracic Echocardiography (TTE)
TTE is the most common type of echocardiogram which involves placing a transducer on the patient's chest, emitting sound waves to create heart images. TTE is invaluable for evaluating the heart's size, structure, and motion, making it particularly useful for...
01:17Imaging Studies for Cardiovascular System I:Echocardiography
Indications: Echocardiography is utilized to diagnose heart failure, valve disorders, and myocardial infarction. It also assesses cardiac structures' size, shape, and motion,...